{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:15:41Z","timestamp":1763442941566,"version":"3.45.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Gestational diabetes mellitus (GDM) and hypertensive disorders of pregnancy (HDP) often coexist and share pathophysiological features such as insulin resistance and endothelial dysfunction, increasing the risk of preterm birth. However, few predictive models have focused specifically on this high-risk group. This study aimed to develop and externally validate a machine learning model for this high-risk population and assess its clinical utility and interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective dual-center study included electronic medical records from 121 and 136 pregnant women with comorbid GDM and HDP, which served as the development and external validation cohorts, respectively. Multiple machine learning algorithms, including Least Absolute Shrinkage and Selection Operator (LASSO) regression, Random Forest (RF), and Naive Bayes (NB), were applied to construct predictive models. To address class imbalance and enhance model robustness, the Synthetic Minority Over-sampling Technique (SMOTE, which generates synthetic samples for the minority class to balance imbalanced datasets) was employed. Model interpretability was further assessed using Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Thirteen variables with univariate significance were entered into Elastic Net regression, yielding five key predictors: alanine transaminase (ALT), aspartate transaminase (AST), Albumin, lactate dehydrogenase (LDH), and systolic blood pressure at 32 \u2013 36 weeks (SBP_32_36). While the LASSO model achieved the highest area under the receiver operating characteristic curve (AUC, 0.802), the NB model demonstrated greater clinical net benefit, higher reclassification performance as measured by the Net Reclassification Improvement (NRI, which evaluates whether patients are more accurately assigned to higher- or lower-risk groups, which reflects the average improvement in distinguishing high-risk from low-risk patients) and Integrated Discrimination Improvement (IDI), and greater robustness in SMOTE-based sensitivity analyses. In the external validation cohort (n = 136), it maintained strong generalization with an AUC of 0.777 (95% confidence interval [CI]: 0.645\u20130.887), accuracy of 0.801 (95% CI: 0.735\u20130.860), sensitivity of 0.792, and specificity of 0.804, supporting its selection as the optimal model for this high-risk population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The Naive Bayes model exhibited robust predictive ability and interpretability for identifying preterm birth risk in pregnancies with comorbid GDM and HDP, and may serve as a transparent, clinically applicable tool for individualized obstetric risk management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2025.1665935","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:13:28Z","timestamp":1763442808000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An explainable machine learning model for predicting preterm birth in pregnant women with gestational diabetes mellitus and hypertensive disorders of pregnancy: development and external validation"],"prefix":"10.3389","volume":"16","author":[{"given":"Landan","family":"Kang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenchi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojing","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-022-00734-y","article-title":"A global view of hypertensive disorders and diabetes mellitus during pregnancy","volume":"18","author":"Jiang","year":"2022","journal-title":"Nat Rev Endocrinol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2021.109050","article-title":"IDF Diabetes Atlas: Estimation of global and regional gestational diabetes mellitus prevalence for 2021 by International Association of Diabetes in Pregnancy Study Group\u2019s criteria","volume":"183","author":"Wang","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fgwh.2025.1533843","article-title":"Global, regional, and national trends and burden of hypertensive disorders in pregnancy among women of childbearing age from 1990 to 2021","volume":"6","author":"Tang","year":"2025","journal-title":"Front Glob Womens Health"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-96345-0","article-title":"Population-based study on birth outcomes among women with hypertensive disorders of pregnancy and gestational diabetes mellitus","volume":"11","author":"Lin","year":"2021","journal-title":"Sci Rep"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-023-05552-2","article-title":"The effect of 2016 Chinese second-child policy and different maternal age on pregnancy outcomes in Hebei Province, China","volume":"23","author":"Tian","year":"2023","journal-title":"BMC Pregnancy Childbirth"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgaa127","article-title":"Association between maternal normal range HbA1c values and adverse birth outcomes","volume":"105","author":"Bi","year":"2020","journal-title":"J Clin Endocrinol Metab"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2023.2296366","article-title":"Association of pre-\/early pregnancy high blood pressure and pregnancy outcomes: a systematic review and meta-analysis","volume":"37","author":"Ma","year":"2024","journal-title":"J Matern Fetal Neonatal Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s12958-021-00751-y","article-title":"Proteinuria may be an indicator of adverse pregnancy outcomes in patients with preeclampsia: a retrospective study","volume":"19","author":"Tang","year":"2021","journal-title":"Reprod Biol Endocrinol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1186\/s12916-023-03171-4","article-title":"Risk factors for preterm birth: an umbrella review of meta-analyses of observational studies","volume":"21","author":"Mitrogiannis","year":"2023","journal-title":"BMC Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12031096","article-title":"Impact of gestational diabetes and hypertension disorders of pregnancy on neonatal outcomes in twin pregnancies based on chorionicity","volume":"12","author":"Liu","year":"2023","journal-title":"J Clin Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1080\/10543400903572829","article-title":"Practical issues in building risk-predicting models for complex diseases","volume":"20","author":"Kang","year":"2010","journal-title":"J Biopharm Stat"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3760\/cma.j.cn112141-20210917-00528","article-title":"Guidelines for diagnosis and treatment of hyperglycemia in pregnancy (2022) [Part I","volume":"57","year":"2022","journal-title":"Chin J Obstet Gynecol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn112141-20200114-00039","article-title":"Guidelines for diagnosis and treatment of hypertensive disorders in pregnancy (2020)","volume":"55","year":"2020","journal-title":"Chin J Obstet Gynecol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn112141-20231119-00208","article-title":"Clinical guidelines for the prevention and treatment of preterm birth (2024 version)","volume":"59","year":"2024","journal-title":"Chin J Obstet Gynecol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/nu12092838","article-title":"The influence of maternal BMI on adverse pregnancy outcomes in older women","volume":"12","author":"Lewandowska","year":"2020","journal-title":"Nutrients"},{"key":"B17","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1186\/s12884-021-03718-4","article-title":"Parity and the risks of adverse birth outcomes: a retrospective study among Chinese","volume":"21","author":"Lin","year":"2021","journal-title":"BMC Pregnancy Childbirth"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2023.2183761","article-title":"Comparison of pregnancy outcomes between IVF-ET and spontaneous pregnancies in women of advanced maternal age","volume":"36","author":"Lang","year":"2023","journal-title":"J Matern Fetal Neonatal Med"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0_11","article-title":"Selection of main effects","volume-title":"Clinical Prediction Models","author":"Steyerberg","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2016.17.3.339","article-title":"How to develop, validate, and compare clinical prediction models involving radiological parameters: study design and statistical methods","volume":"17","author":"Choi","year":"2016","journal-title":"Korean J Radiol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.116.003497","article-title":"Preeclampsia and future cardiovascular health: a systematic review and meta-analysis","volume":"10","author":"Wu","year":"2017","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1177\/10998004211025641","article-title":"Systematic review of prediction models for preterm birth using CHARMS","volume":"23","author":"Kim","year":"2021","journal-title":"Biol Res Nurs"},{"key":"B23","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12884-023-06220-1","article-title":"Machine learning models for predicting preeclampsia: a systematic review","volume":"24","author":"Ranjbar","year":"2024","journal-title":"BMC Pregnancy Childbirth"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/s11906-024-01297-1","article-title":"Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review","volume":"26","author":"Tiruneh","year":"2024","journal-title":"Curr Hypertens Rep"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajogmf.2024.101391","article-title":"Interpretable machine learning predicts postpartum hemorrhage with severe maternal morbidity in a lower-risk laboring obstetric population","volume":"6","author":"Lengerich","year":"2024","journal-title":"Am J Obstet Gynecol MFM"},{"key":"B26","doi-asserted-by":"publisher","first-page":"22620","DOI":"10.1038\/s41598-021-02198-y","article-title":"Machine learning approach for the prediction of postpartum hemorrhage in vaginal birth","volume":"11","author":"Akazawa","year":"2021","journal-title":"Sci Rep"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to decision curve analysis","volume":"3","author":"Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-024-06772-w","article-title":"Establishment and validation of a predictive model for spontaneous preterm birth","volume":"24","author":"Lv","year":"2024","journal-title":"BMC Pregnancy Childbirth"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2022.2160627","article-title":"Elevated liver enzymes and adverse outcomes among patients with preeclampsia with severe features","volume":"36","author":"Greiner","year":"2023","journal-title":"J Matern Fetal Neonatal Med"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2020.35.e198","article-title":"Elevated alanine aminotransferase in early pregnancy and the risk of gestational diabetes and preeclampsia","volume":"35","author":"Lee","year":"2020","journal-title":"J Korean Med Sci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1016\/S1701-2163(16)35048-4","article-title":"Abnormal liver function tests as predictors of adverse maternal outcomes in women with preeclampsia","volume":"33","author":"Kozic","year":"2011","journal-title":"J Obstet Gynaecol Can"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.18999\/nagjms.83.4.741","article-title":"Association between hypoalbuminemia and endothelial dysfunction in preeclampsia","volume":"83","author":"Saitou","year":"2021","journal-title":"Nagoya J Med Sci"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijoa.2023.103963","article-title":"Maldistribution of fluid in preeclampsia: a secondary kinetic analysis","volume":"57","author":"Hahn","year":"2024","journal-title":"Int J Obstet Anesth"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s13224-011-0093-9","article-title":"Lactic dehydrogenase: a biochemical marker for preeclampsia-eclampsia","volume":"61","author":"Jaiswar","year":"2011","journal-title":"J Obstet Gynaecol India"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1097\/HJH.0000000000000370","article-title":"Blood pressure change across pregnancy and risk of hypertensive disorders: findings from a prospective cohort","volume":"33","author":"Macdonald-Wallis","year":"2015","journal-title":"J Hypertens"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1111\/j.1471-0528.2009.02136.x","article-title":"Maternal risk factors for pre-eclampsia in women with chronic hypertension","volume":"116","author":"Poon","year":"2009","journal-title":"BJOG"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32335-7","article-title":"Pre-eclampsia","volume":"398","author":"Chappell","year":"2021","journal-title":"Lancet"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-025-07633-w","article-title":"Integrating SHAP analysis with machine learning to predict postpartum hemorrhage in vaginal births","volume":"25","author":"Song","year":"2025","journal-title":"BMC Pregnancy Childbirth"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1665935\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:13:31Z","timestamp":1763442811000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1665935\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":39,"alternative-id":["10.3389\/fendo.2025.1665935"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1665935","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"article-number":"1665935"}}